Delay Tolerant Network Routing as a Machine Learning Classification Problem
| Autor: | Rachel Dudukovich, Christos A. Papachristou |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Delay-tolerant networking
business.industry Computer science ComputerSystemsOrganization_COMPUTER-COMMUNICATIONNETWORKS 020206 networking & telecommunications 02 engineering and technology NASA Deep Space Network Set (abstract data type) Statistical classification Open research 020204 information systems Path (graph theory) 0202 electrical engineering electronic engineering information engineering Routing (electronic design automation) business Software architecture Computer network |
| Zdroj: | AHS |
| DOI: | 10.1109/ahs.2018.8541460 |
| Popis: | This paper discusses a machine learning-based ap- proach to routing for delay tolerant networks (DTNs) [1]. DTNs are networks which experience frequent disconnections between nodes, uncertainty of an end-to-end path, long one-way trip times, and may have high error rates and asymmetric links. Such networks exist in deep space satellite networks, very rural environments, disaster areas and underwater environments. In this work, we use machine learning classifiers to predict a set of neighboring nodes which are the most likely to deliver a message to a desired location based on message history delivery information. We use the Common Open Research Emulator (CORE) [2] to emulate the DTN environment based on real-world location traces and collect network traffic statistics from the Bundle Protocol implementation IBR-DTN [3]. The software architecture for classification-based routing, analysis and preparation of the network history data and prediction results are discussed. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|